Program Analysis and Machine Learning–based Approach to Predict Power Consumption of CUDA Kernel

Graphics Processing Unit (GPU) has emerged as a popular computing device to achieve Exa-scale performance in High-Performance Computing (HPC) applications. While the power-performance ratio is relatively high for a GPU, it still draws a significant amount of power during computation. In this paper, we propose a preliminary power prediction model which can be used by developers for building power-efficient GPU applications. Using this proposed work, developers can estimate the power consumption of a GPU application during implementation without having to execute it on actual hardware. Our model combines the information derived from static analysis of a CUDA program and a machine learning-based model. We have utilised decision tree technique to validate results across three different GPU architectures: Kepler, Maxwell and Volta. Observed <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$R^{2}$</tex> score value using the decision tree model is 0.8973 for Volta architecture.

Accurately predicting thermophysical properties across various physical states is essential for both industrial and scientific applications. However, experimental data often exhibit variability and noise, requiring robust modeling approaches. In this work, we employ machine learning (ML) techniques to predict methane's thermophysical properties in liquid, vapor, and supercritical phases, including isobaric and isochoric heat capacities, density, specific volume, Joule-Thomson coefficients, enthalpies, sound speed, and shear viscosities, applying an approach recently developed [ACS Eng. Au 5, 226 (2025)10.1021/acsengineeringau.5c00001]. We explore various ML algorithms, including Adaptive Boosting, Bagging, Decision Trees, Extra Trees, Gradient Boosting, Histogram-based Gradient Boosting Regression Tree, K-Nearest Neighbors, Light Gradient Boosting Machine, Nu-Support Vector Regression, Random Forest, Extreme Gradient Boosting, and Artificial Neural Networks. The ML models, which use raw experimental data without removing outliers, produce predictions that are closer to those obtained from the equations of state (EOS) employed by the National Institute of Standards and Technology than to the same raw experimental data used as input for developing the EOS. These results highlight ML's potential to identify and generalize complex patterns, smooth inherent noise, and manage the variability of different thermophysical properties. They indicate that ML models, particularly Extra Trees and Gradient Boosting, can offer a scalable alternative for thermophysical property predictions, offering consistency and efficiency over traditional methods. Although our approach does not eliminate preprocessing, it demonstrates that ML can effectively manage noisy data independently, offering a more efficient and cost-effective alternative to conventional pre- and postprocessing techniques.

The ubiquity of graphics processing unit (GPU) architectures has made them efficient alternatives to chip-multiprocessors for parallel workloads. GPUs achieve superior performance by making use of massive multi-threading and fast context-switching to hide pipeline stalls and memory access latency. However, recent characterization results have shown that general purpose GPU (GPGPU) applications commonly encounter long stall latencies that cannot be easily hidden with the large number of concurrent threads/warps. This results in varying execution time disparity between different parallel warps, hurting the overall performance of GPUs -- the warp criticality problem. To tackle the warp criticality problem, we propose a coordinated solution, criticality-aware warp acceleration (CAWA), that efficiently manages compute and memory resources to accelerate the critical warp execution. Specifically, we design (1) an instruction-based and stall-based criticality predictor to identify the critical warp in a thread-block, (2) a criticality-aware warp scheduler that preferentially allocates more time resources to the critical warp, and (3) a criticality-aware cache reuse predictor that assists critical warp acceleration by retaining latency-critical and useful cache blocks in the L1 data cache. CAWA targets to remove the significant execution time disparity in order to improve resource utilization for GPGPU workloads. Our evaluation results show that, under the proposed coordinated scheduler and cache prioritization management scheme, the performance of the GPGPU workloads can be improved by 23% while other state-of-the-art schedulers, GTO and 2-level schedulers, improve performance by 16% and -2% respectively.

For effective management of water quantity and quality, it is absolutely essential to estimate the pollution level of the existing surface water. This case study aims to evaluate the performance of twelve machine learning (ML) models, including five boosting-based algorithms (adaptive boosting, gradient boosting, histogram-based gradient boosting, light gradient boosting, and extreme gradient boosting), three decision tree-based algorithms (decision tree, extra trees, and random forest), and four ANN-based algorithms (multilayer perceptron, radial basis function, deep feed-forward neural network, and convolutional neural network), in estimating the surface water quality of the La Buong River in Vietnam. Water quality data at four monitoring stations alongside the La Buong River for the period 2010–2017 were utilized to calculate the water quality index (WQI). Prediction performance of the ML models was evaluated by using two efficiency statistics (i.e., R2 and RMSE). The results indicated that all twelve ML models have good performance in predicting the WQI but that extreme gradient boosting (XGBoost) has the best performance with the highest accuracy (R2 = 0.989 and RMSE = 0.107). The findings strengthen the argument that ML models, especially XGBoost, may be employed for WQI prediction with a high level of accuracy, which will further improve water quality management.

Graphic Processing Units (GPUs) have become the accelerator of choice for improving the performance of many of the most demanding applications. While performance of these devices continues to improve generation after generation, reliability of these devices has not been studied rigorously. Several sources of errors can undermine the reliability of these devices, including radiation-induced transient faults, environmental perturbations, and process, temperature or voltage variations. In particular, transient faults in GPU execution have become a significant threat to high performance computing (HPC) and safety-critical applications. HPC systems experience transient faults every few tens of hours and the trend is expected to become worse. A key point in the study of transient faults and their effects on user programs is that some faults do not cause undesirable results in the affected programs. This is especially true for GPU applications. Past efforts to study and understand GPU vulnerability to transient faults have demonstrated reliability can vary greatly across different applications. A significant amount of resilience resides intrinsically in some GPU applications. Transient faults in these applications are not likely to affect the results they produce. Other applications are highly sensitive to transient faults and are likely to crash or produce incorrect results when they are affected by transient faults. While it is generally a good idea to protect the GPU hardware from transient faults, the penalties incurred in terms of performance, power and area are not always justifiable, depending on the applications utilizing the hardware resources. Understanding the relationship between the underlying program characteristics and their implications on vulnerability is crucial. The inherent resilience in applications should be carefully considered when making decisions about designing protection mechanisms to guard against nefarious transient faults. In this thesis, we focus on program characteristics that contribute to their vulnerability. We offer several methodologies that aim at alleviating the prohibitively expensive process of quantifying and estimating the vulnerability of GPU applications, as this is the first step toward improving the reliability of GPUs. Our analyses also demonstrate that beyond the variability between the vulnerabilities of different applications, the vulnerability of GPU applications also varies during their runtime, and present a phase behavior. This phase behavior opens new opportunities for not only more efficient vulnerability estimation, but also more efficient fault mitigation approaches. We demonstrate a methodology for application designers to reduce the cost of protection against transient faults.

Accurate prediction of grid voltage and stability is critical for ensuring reliable and efficient operation of modern power systems, especially with the increasing integration of intermittent renewable energy sources. This study rigorously evaluates five Machine Learning (ML) models, viz., Random Forest (RF), Extra Trees (ET), Support Vector Regression (SVR), Cat Boost (CB), and Gradient Boosting (GB), for their predictive performance in grid connected hybrid PV systems. Using a multimetric framework (R2, MAE, RMSE, MAPE)and advanced visual diagnostics (error distributions, temporal trend analysis),Gradient Boosting emerged as the top performing model, demonstrating superior accuracy and robustness across both voltage and stability prediction tasks. For grid voltage prediction, GB achieved the highest test R2 = 0.9785 and lowest MAPE = 0.25%, with 95% of errors confined to ± 0.5V. In stability score forecasting, GB again outperformed all alternatives, attaining the best R2 = 0.9300 and lowest MAE = 0.75, while maintaining tight residual distributions ± 2.5 units. Comparative analysis revealed GB's consistent superiority over tree based (RF, ET, CB) and kernel based (SVR) models, particularly in handling extreme operational ranges and temporal fluctuations. The results position Gradient Boosting as a unified, high precision solution for smart grid forecasting, offering actionable insights for real time monitoring and control. Its balanced performance across static and dynamic conditions underscores its suitability for resilient grid management in renewable rich environments. This work is novel in generating a controlled MATLAB/ Simulink dataset to capture nonlinear hybrid PV operating regimes and applying correlation-weighted feature engineering to enhance model interpretability. A unified benchmarking of five ML models under identical preprocessing identifies Gradient Boosting as the most reliable predictor. The framework further integrates extended KPIs and dynamic learning-rate scheduling, offering a robust and transparent approach for voltage and stability forecasting. Future research ought to examine hybrid GB ensembles and include optimization to enhance further on scalability with largescale deployments.

Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

The architecture of the latest Graphic Processing Unit (GPU) has surpassed the previous application-specific stream architecture. This has led to an architecture consisting of a number of uniform programmable units integrated on the same chip which facilitate the general-purpose computing beyond the graphic processing. With the multiple programmable units executing in parallel, the latest GPU shows superior performance. Furthermore, programmers can have a direct control on the GPU pipeline using easy-to-use parallel programming environments, whereas they had to rely on specific graphics API's in the past. These advances in hardware and software make General-Purpose GPU (GPGPU) computing widespread. In this paper, using the latest GPU and its software environment, we parallelize a computationally demanding financial application and optimize its performance. We also analyze the performance results compared with those obtained using CPU only. Experimental results show that GPU can achieve a superior performance, greater than 190x, compared with the CPU-only case.

Most Computational Fluid Dynamics (CFD) applications solve the Naiver-Stokes equations using various discretization methods like Finite Difference Method (FDM), Finite Element Method (FEM), Finite Volume Method (FVM), etc. The most compute-intensive process in CFD algorithms is the pressure Poisson solver. Solving the pressure Poisson equation requires the solution of a set of linear simultaneous equations. As the problem size/complexity increases, so does the effort and time invested in solving the equations. This study presents fast and robust iterative solvers and the acceleration of the same using the Graphics Processing Unit (GPU) architecture. Serial versions of the codes are implemented in the C language and the parallelization on GPU is achieved using Compute Unified Device Architecture (CUDA). For this study, a two-dimensional heat conduction problem is considered. FDM is used for discretization. Iterative solvers Conjugate Gradient and Multi Grid methods have been implemented in serial and parallel. The performance enhancement with single GPU and CPU system over a single CPU in terms of computing time is reported. It is seen that multigrid algorithms are superior in convergence and nearly 13 times speed-up has been obtained through GPU acceleration using CUDA, for a grid size of 2048 X 2048. The tests have been done on a cluster with Intel(R) Xeon(R) CPU E5-2670 CPU and NVIDIA K10 GPU.

Optimisation and interpretation of machine and deep learning models for improved water quality management in Lake Loktak

Prognostic methods enable operators and maintainers to predict the future performance for critical systems. However, these methods can be computationally expensive and may need to be performed each time new information about the system becomes available. In light of these computational requirements, we have investigated the application of graphics processing units (GPUs) as a computational platform for real-time prognostics. Recent advances in GPU technology have reduced cost and increased the computational capability of these highly parallel processing units, making them more attractive for the deployment of prognostic software. We present a survey of model-based prognostic algorithms with considerations for leveraging the parallel architecture of the GPU and a case study of GPU-accelerated battery prognostics with computational performance results.

Abstract: Accurate prediction of maximum scour depth (MSD) at sluice gates is critical for guaranteeing the stability and safety of hydraulic systems. Traditional empirical formulas often fail to capture the non-linear interactions between flow dynamics, sediment characteristics, and structural configurations. This study addresses these limitations by leveraging advanced machine learning (ML) techniques, specifically tree-based models, to enhance predictive accuracy. The performance of three tree-based models–Extra Trees (ERT), CatBoost (CAT), and Histogram-Based Gradient Boosting (HGB)–was examined using two hyperparameter tuning methods: Tree-Structured Parzen Estimator (TPE) and Particle Swarm Optimization (PSO). The models underwent 100 simulations to quantify uncertainty and variability in performance metrics. The results indicate that CAT_PSO (optimized with PSO) exhibits superior predictive performance compared to empirical formulas and other ML techniques. CAT_PSO achieved the highest mean CORR (correlation coefficient) of 0.9644 and mean NSE (Nash-Sutcliffe Efficiency) of 0.9272. HGB models demonstrated slightly lower performance compared to CAT and ERT, with higher variability in predictions. Further analysis explored the influence of individual input factors on model performance. The inclusion of more variables, such as tailwater depth and sediment size, generally enhanced model performance. The study also developed new empirical equations for MSD estimation by considering both multiplicative and additive models, progressively incorporating additional input features. These new formulas show improved predictive accuracy over empirical methods, though they still fall short of the performance achieved by the ML models.

The increasing adoption of graphics processing units (GPUs) for high-performance computing raises the reliability challenge, which is generally ignored in traditional GPUs. GPUs usually support thousands of parallel threads and require a sizable register file. Such large register file is highly susceptible to soft errors and power-hungry. Although ECC has been adopted to register file in modern GPUs, it causes considerable power overhead, which further increases the power stress. Thus, an energy-efficient soft-error protection mechanism is more desirable. Besides its extremely low leakage power consumption, resistive memory (e.g., spin-transfer torque RAM) is also immune to the radiation induced soft errors due to its magnetic field based storage. In this article, we propose to LEverage reSistive memory to enhance the Soft-error robustness and reduce the power consumption (LESS) of registers in the General-Purpose computing on GPUs (GPGPUs). Since resistive memory experiences longer write latency compared to SRAM, we explore the unique characteristics of GPGPU applications to obtain the win-win gains: achieving the near-full soft-error protection for the register file, and meanwhile substantially reducing the energy consumption with negligible performance degradation. Our experimental results show that LESS is able to mitigate the registers soft-error vulnerability by 86% and achieve 61% energy savings with negligible (e.g., 1%) performance degradation.

Systematic literature review of machine learning based software development effort estimation models

Nowadays graphics processing units (GPUs) have become popular parallel computing platforms known as General-Purpose GPU (GPGPU) computing. GPUs thereby are chosen by some security researchers as cryptographic accelerators to secure massive volumes of transactions. However, their security issues are ignored in spite of their popularity and performance. There are some possible information leakages faced with malicious attacks or even in the normal GPU computing. Our objective is to secure the confidentiality of cryptographic keys in GPU computing environments and provide easy-to-use programming with few constraints. In this paper, we propose a prototype in Linux, a system of GPGPU computing solution empowered by GPU virtualization technology, which keeps encrypted keys in guest machine to protect secret keys from leakage even in the event of full system compromise. With the API interception and redirection of CUDA, applications in Virtual Machines (VMs) can access the GPU device in a transparent way. Besides, we use virtio, a dedicated virtual I/O device, to transfer data between virtual and host machines in high performance. In our current study, we evaluate our prototype with the GPU implementation of ECC. We show that it can protect private keys of GPU cryptographic computation and it also incurs low performance penalty compared with the native environment, therefore demonstrating the prototype is secure and requires reasonable overhead.